Method for controlling operations of raid system comprising host device and plurality of SSDs

Patent metadata

Field	Value
Publication number	US-11645153-B2
Application number	US-202217872379-A
Country	US
Kind code	B2
Filing date	Jul 25, 2022
Priority date	Apr 23, 2019
Publication date	May 9, 2023
Grant date	May 9, 2023

Abstract

Embodiments herein provide a method for controlling operations of a Redundant Array of Independent Disks (RAID) data storage system comprising a host device and a plurality of solid-state drives (SSDs). The method includes performing, by the at least one SSD, recovery of lost data by performing the auto-rebuild operation. The method also includes performing by the at least one SSD, the auto-error correction operation based on the IO error. The method also includes creating a snapshot of an address mapping table by all SSDs of the plurality of SSDs in the RAID data storage system. The auto-rebuild operation, the auto-error correction operation and the creation the snapshot of the address mapping table are all performed without the intervention from the host device.

First claim

We claim:

1. A method of controlling operations of a Redundant Array of Independent Disks (RAID) data storage system, the RAID data storage system including a host device and a plurality of solid-state drives (SSDs), the method comprising:
when an IO error corresponds to a failure of at least one SSD of the plurality of SSDs,
storing, by the plurality of SSDs, an address mapping table including stripe data in a spare SSD according to failure of a least one of the plurality of SSDs;
performing, by the plurality of SSDs, an auto-rebuild operation in response to an auto-rebuild command received from the host device and including information about the spare SSD; and
sending, by each of the plurality of SSDs, an IO-error correction complete command to the host device.

2. The method of claim 1 , wherein the stripe data in the address mapping table is stored in a controller memory buffer (CMB) of the spare SSD, and
wherein the address mapping table is dynamically updated before receiving, by the plurality of SSDs, the auto-rebuild command.

3. The method of claim 1 , wherein the stripe data indicates addresses of consecutive segments of logically sequential data stored at respective ones of the plurality of SSDs.

4. The method of claim 1 , wherein the plurality of SSDs belong to a single RAID group.

5. The method of claim 1 , wherein, when the IO error does not correspond to the failure of the at least one SSD, the method further comprises:
performing, by the plurality of SSDs, an auto-error correction operation in response to an auto-error correction request received from the host device and including metadata information about the IO error.

6. The method of claim 5 , wherein the performing the auto error correction operation further comprises:
receiving, by at least one SSD from the plurality of SSDs, the auto-error correction request from the host device, the auto-error correction request requesting performance of the auto-error correction operation;
recovering, by the at least one SSD, data from other SSDs in the plurality of SSDs based on the IO error; and
sending, by the at least one SSD, an auto-error correction complete command to the host device after performing the auto-error correction operation.

7. The method of claim 6 , wherein the at least one SSD is configured to recover the data by reading parity data from other SSDs in the plurality of SSDs using a peer-to-peer communication.

8. A method for controlling operations of a Redundant Array of Independent Disks (RAID) data storage system, the RAID system including a host device and a plurality of solid-state drives (SSDs), the method comprising:
detecting, by at least one SSD of the plurality of SSDs, a match between a snapshot version and a timestamp; and
triggering, by the at least one SSD, the plurality of SSDs to create a snapshot of an address mapping table, in response to detecting the match.

9. The method of claim 8 , wherein the address mapping table includes snapshot data of the RAID data storage system, the timestamp, and the snapshot version.

10. The method of claim 8 , wherein the at least one SSD is configured to enable a snapshot feature associated with creating the snapshot in response to a command from the host device.

11. A SSD coupled to a host device in a Redundant Array of Independent Disks (RAID) data storage system, the RAID data storage system including a plurality of solid-state drives (SSDs), the SSD comprising:
a memory;
a processor; and
an auto-rebuild engine, coupled to the memory and the processor, configured to,
receive an auto-rebuild command from the host device when an IO error corresponding to a failure of the SSD is detected, for performing an auto-rebuild operation, wherein the auto-rebuild command comprises information about a spare SSD,
read a stripe data stored at an address mapping table of the spare SSD,
recover lost data by performing the auto-rebuild operation without intervention from the host device, and
send an auto-rebuild complete command to the host device.

12. The SSD of claim 11 , wherein each of the plurality of SSDs receives the auto-rebuild command along with the information of the spare SSD from the host device when the SSD is failed.

13. The SSD of claim 11 , wherein at least one of the plurality of SSDs reads the stripe data from the address mapping table of the spare SSD by performing a peer-to-peer communication with other SSDs in the plurality of SSDs.

14. The SSD of claim 11 , wherein the address mapping table comprising the stripe data is configured in a Controller memory buffer (CMB) of the spare SSD.

15. The SSD of claim 11 , wherein the stripe data indicates addresses of consecutive segments of logically sequential data stored at each of the plurality of SSDs.

16. The SSD of claim 11 , further comprises:
an auto-error correction engine, coupled to the memory and the processor, configured to,
receive an auto-error correction request from the host device for performing an auto-error correction operation, wherein the auto-error correction request comprises information about the IO error,
recover data from other SSDs in the plurality of SSDs by performing the auto-error correction operation based on the IO error, and
send an auto-error correction complete command to the host device.

17. The SSD of claim 16 , wherein the SSD recovers the data by reading parity data from other SSDs in the plurality of SSDs using a peer-to-peer communication.

18. The SSD of claim 11 , further comprises:
an snapshot engine, coupled to the memory and the processor, configured to,
determine a match between a snapshot version and a timestamp, and
trigger to create a snapshot of an address mapping table in response to detecting the match.

19. The SSD of claim 18 , wherein the address mapping table comprises snapshot data of the SSD, the timestamp, and the snapshot version.

20. The SSD of claim 18 , wherein a snapshot feature is enabled by the host device for the SSD.

Assignees

• Samsung Electronics Co Ltd

Inventors

• Shivanand Srikanth Tumkur
• Kodase Sharath Kumar
• Singh Vikram

Classifications

• G06F11/1088 Primary

  Reconstruction on already foreseen single or plurality of spare disks · CPC title

• G06F11/1448

  Management of the data involved in backup or backup restore · CPC title

• G06F11/1471

  involving logging of persistent data for recovery · CPC title

• G06F3/065

  Replication mechanisms · CPC title

• G06F11/1469 Primary

  Backup restoration techniques · CPC title